Research map / 3D vision / 3D generation
BEV-LaneDet: An Efficient 3D Lane Detection Based on Virtual Camera via Key-Points
Ruihao Wang, Jian Qin, Kaiying Li, Yaochen Li, Dong Cao, Jintao Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use BEV-LaneDet instead of PersFormer | 3D lane detection · OpenLane validation, All | F-Score: 47.8 -> 58.4 | Improved |
| Use BEV-LaneDet instead of PersFormer | 3D lane detection · OpenLane | X error far: 0.778 -> 0.659 | Improved |
| Use BEV-LaneDet instead of PersFormer | 3D lane detection · OpenLane | Z error near: 0.213 -> 0.244 | Hurt |
| Use BEV-LaneDet instead of PersFormer | 3D lane detection · Apollo 3D Synthetic, Rarely Observed | F-Score: 87.5 -> 97.6 | Improved |
| Add the Virtual Camera (ablation) | BEV-LaneDet on OpenLane · OpenLane | F-Score: 51.2 -> 54.5(+3.3) | Improved |
| Add the Spatial Transformation Pyramid (ablation) | BEV-LaneDet on OpenLane · OpenLane | F-Score: 51.2 -> 53.2(+2.0) | Improved |
| Add 2D auxiliary supervision (ablation) | BEV-LaneDet on OpenLane · OpenLane | F-Score: 51.2 -> 53.5(+2.3) | Improved |
| Use ResNet18 instead of ResNet34 (ablation) | BEV-LaneDet on OpenLane · OpenLane | F-Score: 58.4 -> 57.8(+6.6) | Hurt |
| Use a 0.05m key-point cell size without offset (ablation) | BEV-LaneDet key-point representation · OpenLane | F-Score: 43.2 | Hurt |
| Use a 0.5m cell size instead of 0.2m without offset (ablation) | BEV-LaneDet key-point representation · OpenLane | F-Score: 55.7 -> 57.9 | Improved |
| Add offset prediction to 0.5m key-point cells (ablation) | BEV-LaneDet key-point representation · OpenLane | X error far: 0.734 -> 0.659 | Improved |
| Add offset prediction to 1m key-point cells (ablation) | BEV-LaneDet key-point representation · OpenLane | X error far: 0.856 -> 0.671 | Improved |
Later papers that compared with this method
3 later accepted papers report BEV-LaneDet as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- SGC-Lane: Monocular 3D Lane Detection with Standard-Definition Map Guidance and Lane Completion (ECCV 2026 · better on 1 of 1 shared result)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · better on 1 of 1 shared result)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · better on 2 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation (ICLR 2024 · similarity 0.90)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (AAAI 2024 · similarity 0.90)
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection (CVPR 2025 · similarity 0.89)
- GLane3D: Detecting Lanes with Graph of 3D Keypoints (CVPR 2025 · similarity 0.89)
- LaneCPP: Continuous 3D Lane Detection using Physical Priors (CVPR 2024 · similarity 0.89)
- A Siamese Transformer with Hierarchical Refinement for Lane Detection (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
